Consider an ensemble learning algorithm that uses simple majority voting among M learned hypotheses (you may...
Fantastic news! We've Found the answer you've been seeking!
Question:
Transcribed Image Text:
Consider an ensemble learning algorithm that uses simple majority voting among M learned hypotheses (you may assume M is odd). Suppose that each hypothesis has error & where 0.5 > >0 and that the errors made by each hypothesis are independent of the others'. Show your work. a. (5 pts) Calculate a formula for the error of the ensemble algorithm in terms of M and E. The ensemble makes an error just in case (M+1)/2 or more hypotheses make an error simultaneously. Recall that the probability that exactly k hypotheses make an error is P(exactly k hypotheses make an error) = (M) *(1-ɛ) (M-k) where (), read "M choose k," is the number of distinct ways of choosing k distinct objects from a set of M distinct objects, calculated as (1) where x!, read "x factorial," is x!= 1*2*3*...*x. Then, M! k!(M-k)! P(error) = E=(M+1)/2 P (exactly k hypotheses make an error) = E=(M+1)/2() Ek(1-E) (M-k) b. (5 pts) Evaluate it for the cases where M = 5, 11, and 21 and c = 0.1, 0.2, and 0.4. M=5 M=11 M=21 0.00856 2.98e-4 1.35e-6 0.0579 0.0117 9.70e-4 0.317 0.247 0.174 -0.1 € 0.2 -0.4 c. (5 pts) If the independence assumption is removed, is it possible for the ensemble error to be worse than &? Produce either an example or a proof that it is not possible. YES. Suppose M=3 and ε = 0.4 = 2/5. Suppose the ensemble predicts five examples el...e5 as follows. el: M1 and M2 are in error, so they out-vote M3 and the prediction of el is in error. e2: M1 and M3 are in error, so they out-vote M2 and the prediction of e2 is in error. e3: M2 and M3 are in error, so they out-vote M1 and the prediction of e3 is in error. e4, e5: None of the hypotheses make an error on e4 or e5, so the predictions of e4 and e5 are correct. The result is that each hypothesis has made 2 errors out of 5 predictions, for an error on each hypothesis of 2/5 = 0.4 = &, as stated. However, the ensemble has made 3 errors out of 5 predictions, for an error on the ensemble of 3/5=0.6>=0.4. Consider an ensemble learning algorithm that uses simple majority voting among M learned hypotheses (you may assume M is odd). Suppose that each hypothesis has error & where 0.5 > >0 and that the errors made by each hypothesis are independent of the others'. Show your work. a. (5 pts) Calculate a formula for the error of the ensemble algorithm in terms of M and E. The ensemble makes an error just in case (M+1)/2 or more hypotheses make an error simultaneously. Recall that the probability that exactly k hypotheses make an error is P(exactly k hypotheses make an error) = (M) *(1-ɛ) (M-k) where (), read "M choose k," is the number of distinct ways of choosing k distinct objects from a set of M distinct objects, calculated as (1) where x!, read "x factorial," is x!= 1*2*3*...*x. Then, M! k!(M-k)! P(error) = E=(M+1)/2 P (exactly k hypotheses make an error) = E=(M+1)/2() Ek(1-E) (M-k) b. (5 pts) Evaluate it for the cases where M = 5, 11, and 21 and c = 0.1, 0.2, and 0.4. M=5 M=11 M=21 0.00856 2.98e-4 1.35e-6 0.0579 0.0117 9.70e-4 0.317 0.247 0.174 -0.1 € 0.2 -0.4 c. (5 pts) If the independence assumption is removed, is it possible for the ensemble error to be worse than &? Produce either an example or a proof that it is not possible. YES. Suppose M=3 and ε = 0.4 = 2/5. Suppose the ensemble predicts five examples el...e5 as follows. el: M1 and M2 are in error, so they out-vote M3 and the prediction of el is in error. e2: M1 and M3 are in error, so they out-vote M2 and the prediction of e2 is in error. e3: M2 and M3 are in error, so they out-vote M1 and the prediction of e3 is in error. e4, e5: None of the hypotheses make an error on e4 or e5, so the predictions of e4 and e5 are correct. The result is that each hypothesis has made 2 errors out of 5 predictions, for an error on each hypothesis of 2/5 = 0.4 = &, as stated. However, the ensemble has made 3 errors out of 5 predictions, for an error on the ensemble of 3/5=0.6>=0.4.
Expert Answer:
Answer rating: 100% (QA)
a The ensemble makes an error just in case M12 or more hypotheses make an error simultaneously The p... View the full answer
Related Book For
Elementary Statistics
ISBN: 978-0538733502
11th edition
Authors: Robert R. Johnson, Patricia J. Kuby
Posted Date:
Students also viewed these computer engineering questions
-
Characterize the errors made by William Blackwell and Madison Wells as either "honest mistakes," negligence, or recklessness. Defend each of your characterizations.
-
Consider the simple regression yt = xt + 1 where E p[ | x] = 0 and E [2 | x ] = 2 (a) What is the minimum mean squared error linear estimator of ? Choose e to minimize Var [] + [E( ?? )]2. The answer...
-
Consider a database with objects X and Y and assume that there are two transactions T1 and T2. Transaction T1 reads objects X and Y and then writes object X. Transaction T 2 reads objects X and Y and...
-
Mrs Anh Thuy is a 43 year old lady admitted following an incidence of blurred vision, numbness down the right side and a sharp pain in her head. A neighbour found her on the ground unable to move or...
-
Each morning, Nate Jeppson stocks the drink case at Nates Beach Hut in Long Beach, California. Nates Beach Hut has 110 linear feet of refrigerated display space for cold drinks. Each linear foot can...
-
Your airplane crashes in the Pacific Ocean. You land on a desert island with one other passenger. A box containing 100 little bags of peanuts also washes up on the island. The peanuts are the only...
-
The Oasis Hotel is planning its cash payments for operations for the fourth quarter (October-December), 2003. The Accrued Expenses Payable balance on October 1 is \($136,000.\) The budgeted expenses...
-
Ringer Foods produces specialty soup sold in jars. The projected sales in dollars and jars for each quarter of the upcoming year are as follows: Ringer anticipates selling 220,000 jars with total...
-
DATA MODEL (REA) EXERCISE Laguna Beach RENTALS (Purchase/ Acquisition Cycle) use the information below and the list of attributes at the end (no additions) to draw one REA diagram for each part...
-
Returning to problem 5, now assume that the products to be removed are strategicin the sense that they drive sales from some key customersand also that their wholesale price is \($70\) (instead of...
-
The pharmacy at Metropolitan Hospital receives 12 requests for prescriptions each hour, Poisson distributed. It takes the staff a mean time 4 minutes to fill each following a negative exponential...
-
A local management consulting firm is preparing a business report for the Government of Alberta. In particular, you have been hired by that firm to calculate the weighted average cost of capital (...
-
San Jose Company operates a Manufacturing Division and an Assembly Division. Both divisions are evaluated as profit centers. Assembly buys components from Manufacturing and assembles them for sale....
-
The management of Winstead Corporation is considering the following three investment projects (Ignore income taxes.): Project R $ 84,900 Project S $ 150,500 Investment required Project O $ 46,400...
-
A $ 1 , 0 0 0 face amount 8 % convertible bond has a conversion ratio of 2 0 . The firm s common stock is currently selling at $ 4 0 . If the bond is about to mature, what is its value?
-
A stock has a real rate of return of 1 5 . 7 % and during the past year, inflation was 2 . 9 % . What was the stocks nominal rate of return ?
-
0 F -3 m- -1 m 1 m
-
Subtract the polynomials. (-x+x-5) - (x-x + 5)
-
A computer was used to construct this dotplot below. a. How many data values are shown? b. List the values of the five smallest data. c. What is the value of the largest data item? d. What value...
-
Many organizations offer special magazine rates to their members. The American Federation of Teachers is no different, and here are a few of the rates they offer their members. a. Construct a scatter...
-
Ronald Fisher, an English statistician (18901962), collected measurements for a sample of 150 irises. Of concern were five variables: species, petal width (PW), petal length (PL), sepal width (SW),...
-
A generalization of both the gamma and inverse-gamma distribution is the generalized inverse-gamma distribution, which has density \[ \begin{equation*} f(s)=\frac{(a / b)^{p / 2}}{2 K_{p}(\sqrt{a...
-
A \(d\)-dimensional normal random vector \(X \sim \mathscr{N}\left(\boldsymbol{\mu}, \sum ight)\) can be defined via an affine transformation, \(\boldsymbol{X}=\boldsymbol{\mu}+\boldsymbol{\Sigma}^{1...
-
Consider the ellipsoid \(E=\left\{\boldsymbol{x} \in \mathbb{R}^{d}: x \boldsymbol{\Sigma}^{-1} \boldsymbol{x}=1 ight\}\) in (4.42). Let \(\mathbf{U D}^{2} \mathbf{U}^{\top}\) be an SVD of...
Study smarter with the SolutionInn App